Repositories · organized/repo_cards

仓库/Skill 库

16 个 · Agent 智能体 · 框架 · 快速增长

排序 Stars 周增
obra/superpowers
Shell · 2026-08-08 Agent 智能体 框架 生产可用 Stars 270347 周增 +1484

一个切实可用的 agentic skills 框架与软件开发方法论An agentic skills framework & software development methodology that works.

agent
n8n-io/n8n
TypeScript · 2026-08-11 Agent 智能体 框架 生产可用 Stars 200219 周增 +350

Fair-code 工作流自动化平台,原生具备 AI 能力。融合可视化搭建与自定义代码,支持自托管或云端,400+ 集成。Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.

langgenius/dify
TypeScript · 2026-08-20 Agent 智能体 框架 生产可用 Stars 152959 周增 +678

可直接用于生产环境的 Agent 工作流开发平台。Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype to production without rebuilding the stack.

agentragengineeringllm-infra
langchain-ai/langchain
Python · 2026-08-11 Agent 智能体 框架 生产可用 Stars 143933 周增 +259

Agent 工程平台。The agent engineering platform.

agentragllm-infra
farion1231/cc-switch
Rust · 2026-08-11 Agent 智能体 框架 生产可用 Stars 126267 周增 +560

跨平台桌面 All-in-One 助手,支持 Claude Code、Codex、OpenCode、OpenClaw、Gemini CLI 与 Hermes Agent。唯一官网:ccswitch.ioA cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Grok Build & Hermes Agent. Only official website: ccswitch.io

agent
mastra-ai/mastra
TypeScript · 2026-08-24 Agent 智能体 框架 生产可用 Stars 27434 周增 +206

Mastra 是面向 AI 驱动的应用与 agents 的现代 TypeScript 框架。Mastra is the modern TypeScript framework for AI-powered applications and agents.

agentllm-infra
andrewyng/openworker
Python · 2026-08-08 Agent 智能体 框架 研究原型 Stars 14114 周增 +329
omnigent-ai/omnigent
Python · 2026-08-08 Agent 智能体 框架 生产可用 Stars 8412 周增 +140

Omnigent 是一个开源 AI agent 框架与元 harness:编排 Claude Code、Codex、Cursor、Pi 及自定义 agent——无需重写即可替换 harness,强制执行策略与沙箱化,并支持任意设备实时协作。Omnigent is an open-source AI agent framework and meta-harness: orchestrate Claude Code, Codex, Cursor, Pi, and custom agents — swap harnesses without rewriting, enforce policies and sandboxing, and collaborate in real time from any device.

agentmultimodalllm-infra
elder-plinius/T3MP3ST
TypeScript · 2026-08-02 Agent 智能体 框架 研究原型 Stars 5520 周增 +70

自主红队平台;多 Agent 攻击性安全元框架autonomous red teaming platform; multi-agent offensive-security meta-harness

agentrisk
XBuilderLAB/cheat-on-content
Python · 2026-06-27 Agent 智能体 框架 生产可用 Stars 5222 周增 +42

你正在读这段文字,skill 已经预测到了。一个把每条帖子转化为校准实验的工作流——打分、盲预测、复盘、迭代。未来不奖励努力,只奖励先看见模式的人。一个月 100 万粉丝——不是运气,是系统。You're reading this. The skill predicted it. A workflow that turns every post into a calibrated experiment—score, blind-predict, retro, evolve. The future doesn't reward effort, it rewards those who see the pattern first. 1M followers in a month — not luck, system.

vercel/eve
TypeScript · 2026-08-11 Agent 智能体 框架 研究原型 Stars 4529 周增 +70

构建 Agent 的开源框架The Open Framework for Building Agents

agent
OpenBMB/PilotDeck
TypeScript · 2026-07-18 Agent 智能体 框架 研究原型 Stars 3849 周增 +28

面向任务的 AI Agent 生产力平台Task-oriented AI Agent productivity platform

agent
b-nnett/goose
Rust · 2026-06-02 Agent 智能体 框架 实验 Stars 2679 周增 +0

Goose Swift 概念验证 README。Goose Swift proof-of-concept README

yetone/cumora
TypeScript · 2026-08-19 Agent 智能体 框架 研究原型 Stars 2488 周增 +0

Agent 团队的聚集地。跨平台团队聊天工具,AI Agent 作为一等队友 — 支持云端大脑或自带大脑(Claude Code / Codex)。Where agent teams gather. Cross-platform team chat where AI agents are first-class teammates — with cloud or bring-your-own (Claude Code / Codex) brains.

agent
Apeireth/apeireth-rust
Rust · 2026-08-24 Agent 智能体 框架 实验 Stars 107 周增 +42

Apeireth——AGI 操作系统 / LLM 基础(Rust)。85 个 crate:companion organ、world model、好奇心、假设检验、双层洋葱安全。Apeireth — An AGI Operating System / LLM Base (Rust). 85 crates: companion organ, world model, curiosity, hypothesis testing, double-onion security.

riskllm-infra
YintaTriss/apeireth-rust
Rust · 2026-08-21 Agent 智能体 框架 实验 Stars 53 周增 +0

Apeireth——一款基于 Rust 的 AGI 操作系统 / LLM 基座。85 个 crate:陪伴器官、世界模型、好奇心、假设检验、双层洋葱式安全Apeireth — An AGI Operating System / LLM Base (Rust). 85 crates: companion organ, world model, curiosity, hypothesis testing, double-onion security.

riskllm-infra